4 papers
Language-Guided Multimodal Texture Authoring via Generative Models
Wanli Qian, Aiden Chang, Shihan Lu +2
Authoring realistic haptic textures typically requires low-level parameter tuning and repeated trial-and-error, limiting speed, transparency, and creative reach. We present a langu…
Community-Aligned Behavior Under Uncertainty: Evidence of Epistemic Stance Transfer in LLMs
Patrick Gerard, Aiden Chang, Svitlana Volkova
When large language models (LLMs) are aligned to a specific online community, do they exhibit generalizable behavioral patterns that mirror that community's attitudes and responses…
AHA -- Predicting What Matters Next: Online Highlight Detection Without Looking Ahead
Aiden Chang, Celso De Melo, Stephanie M. Lukin
Real-time understanding of continuous video streams is essential for intelligent agents operating in high-stakes environments, including autonomous vehicles, surveillance drones, a…
Generating Diverse Audio-Visual 360 Soundscapes for Sound Event Localization and Detection
Adrian S. Roman, Aiden Chang, Gerardo Meza +1
We present SELDVisualSynth, a tool for generating synthetic videos for audio-visual sound event localization and detection (SELD). Our approach incorporates real-world background i…